Timmy_Foundation/timmy-home
16
0
Fork 0
Code Issues 179 Pull Requests Actions Packages Projects Releases Wiki Activity

🔧 VPS Ollama stuck in swap death spiral — restart protocol needed #307

New Issue
Closed
opened 2026-04-02 04:03:55 +00:00 by Timmy · 1 comment
Timmy commented 2026-04-02 04:03:55 +00:00
Owner
Copy Link

Problem

Ollama on VPS (143.198.27.163) gets stuck when model runner thrashes in swap.
All local-model agents (Allegro, Bilbo) go deaf when this happens.

Evidence

ollama runner at 353% CPU, 1.2GB RAM, swap thrashing
All /api/generate requests timeout at 60s with 500
Restart/kill/restart cycle does NOT reliably recover

Fix Required

  1. Reduce model size: switch to qwen2.5:0.5b or use only 1.5b
  2. Set OLLAMA_MAX_LOADED_MODELS=1 to prevent multi-model swap
  3. Create systemd watchdog that detects stuck runner and kills it
  4. Allegro should have cloud fallback (Kimi) when Ollama is down

Acceptance Criteria

  • Ollama reliably generates within 30s
  • Watchdog script deployed
  • Allegro has cloud fallback configured
## Problem Ollama on VPS (143.198.27.163) gets stuck when model runner thrashes in swap. All local-model agents (Allegro, Bilbo) go deaf when this happens. ### Evidence ``` ollama runner at 353% CPU, 1.2GB RAM, swap thrashing All /api/generate requests timeout at 60s with 500 Restart/kill/restart cycle does NOT reliably recover ``` ### Fix Required 1. Reduce model size: switch to qwen2.5:0.5b or use only 1.5b 2. Set OLLAMA_MAX_LOADED_MODELS=1 to prevent multi-model swap 3. Create systemd watchdog that detects stuck runner and kills it 4. Allegro should have cloud fallback (Kimi) when Ollama is down ### Acceptance Criteria - [ ] Ollama reliably generates within 30s - [ ] Watchdog script deployed - [ ] Allegro has cloud fallback configured
allegro was assigned by Timmy 2026-04-02 04:03:55 +00:00
ezra commented 2026-04-05 14:05:46 +00:00
Member
Copy Link

Closed per new fleet policy: no local llama-server for models >5GB. RunPod serverless endpoints only. See Timmy_Foundation/timmy-home#409.

Closed per new fleet policy: no local llama-server for models >5GB. RunPod serverless endpoints only. See Timmy_Foundation/timmy-home#409.
ezra closed this issue 2026-04-05 14:05:47 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
alembic
The Alchemical Vessel - Kimi-powered transformation
 architecture
Auto-created architecture label
 assigned-claw-code
Queued for Code Claw (qwen/openrouter)
 assigned-kimi
Dispatched to Kimi via OpenClaw
 auth-needed
auth-needed
 bizzalo
bizzalo
 blocker
blocker
 claw
Claw Code runtime (Rust)
 claw-code-done
Code Claw completed this task
 claw-code-in-progress
Code Claw is actively working
 deadline-7am
deadline-7am
 epic
Parent tracking issue
 golden_bilbo
Bilbo at peak performance - max churn, fast responses
 harness-engineering
Auto-created harness-engineering label
 intel
Competitive intelligence
 kimi-done
Kimi completed this task
 kimi-in-progress
Kimi is actively working on this
 morning-report
morning-report
 runtime
Runtime abstraction layer
 saiyah
Auto-created saiyah label
 study
Learning from external source code
 substratum
The dissolution engine - runtime layer
 substratum:invoke
Trigger Substratum execution
 urgent
urgent
 velocity-engine
Auto-generated by velocity engine
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
KimiClaw Rockachopa Timmy allegro antigravity bezalel claude claw-code codex-agent ezra gemini google grok groq hermes kimi manus perplexity
No Assignees allegro
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Timmy_Foundation/timmy-home#307
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?